| Task Name | Dataset Name | SOTA Result | Trend | |
|---|---|---|---|---|
| Named Entity Recognition | i2b2 | A_T52.36 | 44 | |
| Named Entity Recognition | i2b2 2014 | Micro F1 Score0.5821 | 26 | |
| Named Entity Recognition | I2B2 2010 (test) | Micro F10.7198 | 24 | |
| Clinical concept extraction | i2b2 2010 (test) | Exact F190.25 | 14 | |
| Relation Extraction | I2B2 Three-site experiment (test) | Strict Micro F10.745 | 13 | |
| Named Entity Recognition | I2B2 Three-site experiment (test) | Strict Micro F185.2 | 13 | |
| Relation Extraction | I2B2 Two-site experiment (test) | Strict Micro F174.6 | 13 | |
| Named Entity Recognition | I2B2 Two-site experiment (test) | Strict Micro F186.4 | 13 | |
| Clinical concept extraction | i2b2 2012 (test) | Exact F180.91 | 13 | |
| Named Entity Recognition | i2b2 bert-base-cased (FG-8-PG-2) | At Score56.96 | 11 | |
| Named Entity Recognition | i2b2 FG-8-PG-1 bert-base-cased | At Score50.75 | 11 | |
| Named Entity Recognition | i2b2 FG-2-PG-2 bert-base-cased | At54.84 | 11 | |
| Named Entity Recognition | i2b2 bert-base-cased (FG-1-PG-1) | At Score43.88 | 11 | |
| Clinical NLP Tasks | i2b2 | GPT-4 Score3.36 | 10 | |
| Named Entity Recognition | I2B2 (test) | Micro-F164.3 | 9 | |
| Clinical Relation Extraction | i2b2 English 2010 | Micro F191.8 | 8 | |
| Drug Named Entity Recognition | i2b2 2009 | F1 Score93.2 | 8 | |
| Clinical Relation Extraction | i2b2 Turkish 2010 | Micro F10.87 | 6 | |
| Named Entity Recognition | i2b2-10 | Micro F1 (span-level)87.4 | 6 | |
| Named Entity Recognition | i2b2 2012 | F1 Score80 | 5 | |
| Named Entity Recognition | i2b2 2006 | F1 Score97.4 | 5 | |
| Diagnosis prediction | i2b2 (test) | AUROC82.31 | 4 | |
| Named Entity Recognition | i2b2 2014 (20% test) | Precision96 | 4 | |
| Relation Extraction | i2b2-Clinical (test) | Macro F169.1 | 3 | |
| Relation Extraction | i2b2-Temporal (test) | Macro F173.6 | 3 |